Boeing Colloquium: A Machine Learning Approach to Modeling Human Interaction with Autonomous Systems

Boeing Distinguished Colloquium, October 10, 2019

Missy Cummings
Duke University

Title: A Machine Learning Approach to Modeling Human Interaction with Autonomous Systems

Abstract: There is significant interest in the development and deployment of safety-critical technologies with embedded autonomy. However, most of these systems require some form of human interaction whether it is humans supervising these systems like a drone operator, or people working in and around the system such as pedestrians and driverless cars. This talk will describe an unsupervised learning approach to modeling human interaction with autonomous systems and how such models can be used to diagnose system design issues.